{ "opencollection": "1.0.0", "info": { "name": "Dedalus Audio V1 API", "version": "0.0.1" }, "items": [ { "info": { "name": "V1", "type": "folder" }, "items": [ { "info": { "name": "List Models", "type": "http" }, "http": { "method": "GET", "url": "https://api.dedaluslabs.ai/v1/models", "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "List available models.\n\nRetrieve the complete list of models available to your organization, including\nmodels from OpenAI, Anthropic, Google, xAI, Mistral, Fireworks, and DeepSeek.\n\nReturns:\n ListModelsResponse: List of available models across all supported providers" }, { "info": { "name": "Retrieve Model", "type": "http" }, "http": { "method": "GET", "url": "https://api.dedaluslabs.ai/v1/models/:model_id", "params": [ { "name": "model_id", "value": "", "type": "path" } ], "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Retrieve a model.\n\nRetrieve detailed information about a specific model, including its capabilities,\nprovider, and supported features.\n\nArgs:\n model_id: The ID of the model to retrieve (e.g., 'openai/gpt-4', 'anthropic/claude-3-5-sonnet-20241022')\n user: Authenticated user obtained from API key validation\n\nReturns:\n Model: Information about the requested model\n\nRaises:\n HTTPException:\n - 401 if authentication fails\n - 404 if model not found or not accessible with curren" }, { "info": { "name": "Create Chat Completion", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/chat/completions", "body": { "type": "json", "data": "{}" }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Create a chat completion.\n\nGenerates a model response for the given conversation and configuration.\nSupports OpenAI-compatible parameters and provider-specific extensions.\n\nHeaders:\n - Authorization: bearer key for the calling account.\n - X-Provider / X-Provider-Key: optional headers for using your own provider API key.\n\nBehavior:\n - If multiple models are supplied, the first one is used, and the agent may hand off to another model.\n - Tools may be invoked on the server or signaled for the c" }, { "info": { "name": "Create Embeddings", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/embeddings", "body": { "type": "json", "data": "{}" }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Create embeddings using the configured provider." }, { "info": { "name": "Create Response", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/responses", "body": { "type": "json", "data": "{}" }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Create a response using the OpenAI Responses API.\n\nThis endpoint routes directly to OpenAI's Responses API.\nOnly OpenAI models are supported." }, { "info": { "name": "Create Speech", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/audio/speech", "body": { "type": "json", "data": "{}" }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Generate speech audio from text.\n\nGenerates audio from the input text using text-to-speech models. Supports multiple\nvoices and output formats including mp3, opus, aac, flac, wav, and pcm.\n\nReturns streaming audio data that can be saved to a file or streamed directly to users." }, { "info": { "name": "Create Transcription", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/audio/transcriptions", "body": { "type": "multipart-form", "data": [] }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Transcribe audio into text.\n\nTranscribes audio files using OpenAI's Whisper model. Supports multiple audio formats\nincluding mp3, mp4, mpeg, mpga, m4a, wav, and webm. Maximum file size is 25 MB.\n\nArgs:\n file: Audio file to transcribe (required)\n model: Model ID to use (e.g., \"openai/whisper-1\")\n language: ISO-639-1 language code (e.g., \"en\", \"es\") - improves accuracy\n prompt: Optional text to guide the model's style\n response_format: Format of the output (json, text, srt, verbose_" }, { "info": { "name": "Create Translation", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/audio/translations", "body": { "type": "multipart-form", "data": [] }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Translate audio into English.\n\nTranslates audio files in any supported language to English text using OpenAI's\nWhisper model. Supports the same audio formats as transcription. Maximum file size\nis 25 MB.\n\nArgs:\n file: Audio file to translate (required)\n model: Model ID to use (e.g., \"openai/whisper-1\")\n prompt: Optional text to guide the model's style\n response_format: Format of the output (json, text, srt, verbose_json, vtt)\n temperature: Sampling temperature between 0 and 1\n\nRet" }, { "info": { "name": "Create Image", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/images/generations", "body": { "type": "json", "data": "{}" }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Generate images from text prompts.\n\nPure image generation models only (DALL-E, GPT Image).\nFor multimodal models like gemini-2.5-flash-image, use /v1/chat/completions." }, { "info": { "name": "Edit Image", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/images/edits", "body": { "type": "multipart-form", "data": [] }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Edit images using inpainting.\n\nSupports dall-e-2 and gpt-image-1. Upload an image and optionally a mask\nto indicate which areas to regenerate based on the prompt." }, { "info": { "name": "Create Variation", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/images/variations", "body": { "type": "multipart-form", "data": [] }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Create variations of an image.\n\nDALL·E 2 only. Upload an image to generate variations." }, { "info": { "name": "Process Ocr", "type": "http" }, "http": { "method": "POST", "url": "https://api.dedaluslabs.ai/v1/ocr", "body": { "type": "json", "data": "{}" }, "auth": { "type": "bearer", "token": "{{bearerToken}}" } }, "docs": "Process a document through Mistral OCR.\n\nExtracts text from PDFs and images, returning markdown-formatted content." } ] } ], "bundled": true }